Self-adjustable domain adaptation in personalized ECG monitoring integrated with IR-UWB radar. (January 2019)

• Record Type: Journal Article
• Authors: Yin, Wenfeng; Yang, Xiuzhu; Li, Lei; Zhang, Lin; Kitsuwan, Nattapong; Shinkuma, Ryoichi; Oki, Eiji
• Is Part Of: Biomedical signal processing and control. Volume 47(2019)
• Page Start: 75
• Page End: 87
• Publication Date: 2019-01
• Subjects: 92B20 -- 68T05; Transfer learning -- Domain adaptation -- One-class classification -- Self organizing maps -- ECG monitoring; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2018.08.002
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: A self-adjustable domain adaptation (SADA) strategy is devised against overfitting. SADA builds a vital sign dataset of ECG and IR-UWB radar data by actual records. SADA devises the SOM-based ECG clustering by transfer learning to fuse multi data. SADA broadens the application of domain adaptation algorithms by importing OC-SVM. Abstract: To enhance electrocardiogram (ECG) monitoring systems in personalized detections, deep neural networks (DNNs) are applied to overcome individual differences by periodical retraining. As introduced previously[4], DNNs relieve individual differences by fusing ECG with impulse radio ultra-wide band (IR-UWB) radar. However, such DNN-based ECG monitoring system tends to overfit into personal small datasets and is difficult to generalize to newly collected unlabeled data. This paper proposes a self-adjustable domain adaptation (SADA) strategy to prevent from overfitting and exploit unlabeled data. Firstly, this paper enlarges the database of ECG and radar data with actual records acquired from 28 testers and expanded by the data augmentation. Secondly, to utilize unlabeled data, SADA combines self organizing maps with the transfer learning in predicting labels. Thirdly, SADA integrates the one-class classification with domain adaptation algorithms to reduce overfitting. Based on our enlarged database and standard databases, a large dataset of 73200 records and a small one of 1849 records are built up to verify our proposal. Results show SADA's effectiveness in predicting labels and increments in the sensitivity of DNNs by 14.4% compared with existing domain adaptation algorithms.